leo-pony 13db492f83 Adapt to dynamically loadable backends mechanism (llama/9970) ...

* [CANN] Adapt to dynamically loadable backends mechanism

* Fix the Bug: inference running result is garbled in debug running model for LM models who's type is Q4_0 class

* Handle the review comments of this pull request

2024-11-01 10:19:05 +02:00

..

ggml-alloc.h

ggml : fix typo in example usage ggml_gallocr_new (ggml/984)

2024-10-05 15:23:51 +03:00

ggml-backend.h

ggml : add backend registry / device interfaces to BLAS backend (llama/9752)

2024-11-01 10:19:05 +02:00

ggml-blas.h

ggml : add backend registry / device interfaces to BLAS backend (llama/9752)

2024-11-01 10:19:05 +02:00

ggml-cann.h

Adapt to dynamically loadable backends mechanism (llama/9970)

2024-11-01 10:19:05 +02:00

ggml-cuda.h

ggml-backend : add device and backend reg interfaces (llama/9707)

2024-10-05 15:23:51 +03:00

ggml-kompute.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-metal.h

ggml : add metal backend registry / device (llama/9713)

2024-11-01 10:19:05 +02:00

ggml-rpc.h

rpc : add backend registry / device interfaces (llama/9812)

2024-11-01 10:19:05 +02:00

ggml-sycl.h

Add SYCL Backend registry, device and Event Interfaces (llama/9705)

2024-11-01 10:19:05 +02:00

ggml-vulkan.h

vulkan : add backend registry / device interfaces (llama/9721)

2024-11-01 10:19:05 +02:00

ggml.h

add amx kernel for gemm (llama/8998)

2024-11-01 10:19:05 +02:00